The Segment Anything Model (SAM) is a popular image processing tool for its segmentation accuracy, variety of input prompts, training capabilities, and efficient model design. However, its application to ultrasound images has been challenging due to image noise and the model’s broad training dataset. ClickSAM was developed to address these issues, fine-tuning SAM for ultrasound image segmentation using click prompts. The training of ClickSAM involves a two-stage process focused on improving model performance using positive and negative click prompts. This approach has demonstrated superior performance compared to other existing models for ultrasound image segmentation.
Publication date: 9 Feb 2024
Project Page: not provided
Paper: https://arxiv.org/pdf/2402.05902
